Neural network forecasting for seasonal and trend time series

By G. Zhang, Min Qi. 2005

400 citations recorded by the source corpus.

Subfields: Electrical and Electronic Engineering, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

In Management Science and Operations Research

Citations in the corpus

Forecasting Across Time Series Databases using Long Short-Term Memory Networks on Groups of Similar Series (2017, methodology): “s recurrent neural networks, echo state networks, generalized regression neural networks and ensemble architectures to uplift the constraints of the conventional NN architecture (Nelson et al., 1999; Zhang and Qi, 2005; Ilies et al., 2007; Rahman et al., 2016; Yan, 2012; Zimmermann et al., 2012). Ho”
Anomaly Detection for IoT Time-Series Data: A Survey (2020, methodology): “Another approach to the predictive method is to use arti-ﬁcial neural networks to capture the dynamics of a time series, early multilayer perceptron (MLP) approaches showed similar predictive abilities to those demonstrated in ARMA derivative models [65] for stationary and nonseasonal time series.”
Advances in forecasting with neural networks? Empirical evidence from the NN3 competition on time series prediction (2011, methodology): “…more CI are ranked highly on seasonal data than on non-seasonal data, a second fundamental contradiction to prior research in the form of working hypothesis WH4, which had identified problems in predicting seasonal time series with NNs and proposed prior deseasonalisation (e.g., Zhang & Qi, 2005).”
Neural network ensemble operators for time series forecasting (2014, methodology): “Following the suggestions of the literature, if trend is identiﬁed in a time series it is removed through ﬁrst diﬀerencing (Zhang and Qi, 2005).”
Predicting Citywide Crowd Flows Using Deep Spatio-Temporal Residual Networks (2017, background): “ANNs have excellent nonlinear modeling ability, but not enough for linear modeling ability [35].”
An Empirical Comparison of Machine Learning Models for Time Series Forecasting (2010, methodology): “Many papers consider the issues of preprocessing (Zhang et al [54], Zhang and Qi [55], Miller and Williams [39], and Balkin and Ord [4]), and so they are beyond the scope of this work.”
Forecasting across time series databases using recurrent neural networks on groups of similar series: A clustering approach (2017, methodology): “Recent developments have been mainly around preprocessing techniques such as deseasonalization and detrending to supplement the NN’s learning process, and novel NN architectures such as recurrent neural networks (RNN), echo state networks (ESN), generalized regression neural networks (GRNN) and ense”
TSMixer: An all-MLP Architecture for Time Series Forecasting (2023, background): “First, we consider the common assumption that the time series is periodic (Holt, 2004; Zhang & Qi, 2005).”
A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition (2011, background): “…2006; Anders and Korn, 1999; Chapelle and Vapnik, 2000), eﬀect of deseasonalization (Hylleberg, 1992; Makridakis et al., 1998; Nelson et al., 1999; Zhang and Qi, 2005), forecasts combination (Bates, J. M. and Granger, C. W. J., 1969; Clemen, 1989; Timmermann, 2006) and many other critical topics…”
Forecast combinations of computational intelligence and linear models for the NN5 time series forecasting competition (2011, background): “Zhang and Kline (2007) and Zhang and Qi (2005) arrived at the same conclusion, and showed that deseasonalization (as well as detrending) is very beneficial when using neural network forecasting models.”
Improvement of Auto-Regressive Integrated Moving Average models using Fuzzy logic and Artificial Neural Networks (ANNs) (2009, methodology): “Single hidden layer feed forward network is the most widely used model form for time series modeling and forecasting [70].”
A hybrid ARIMA and artificial neural networks model to forecast particulate matter in urban areas: The case of Temuco, Chile (2008, background): “…2007), ﬁsh catch (Gutie´rrez-Estrada et al., 2007) production values of the machinery industry (Chen and Wang, 2007), ﬁsh community diversity (Gutie´rrez-Estrada et al., 2008), and in other areas (Tseng et al., 2002; Zhang, 2003; Zhang and Qi, 2005), but all of them are not related to air quality.”
Interpolation in Time Series : An Introductive Overview of Existing Methods, Their Performance Criteria and Uncertainty Assessment (2017, background): “Zhang and Qi [49] suggested that a single hidden layer, where neurons are connected with acyclic links, is the most used shape of network for modeling and forecasting in time series.”
An artificial neural network (p, d, q) model for timeseries forecasting (2010, background): “One of the most significant advantages of the ANN models over other classes of nonlinear models is that ANNs are universal approximators that can approximate a large class of functions with a high degree of accuracy (Chen, Leung, & Hazem, 2003; Zhang & Min Qi, 2005).”
Back propagation neural network with adaptive differential evolution algorithm for time series forecasting (2015, methodology): “Artificial neural networks (ANNs) have been extensively studied and used in time series forecasting (Adebiyi, Adewumi, & Ayo, 2014; Bennett, Stewart, & Beal, 2013; Geem & Roper, 2009; Zhang, Patuwo, & Hu, 2001; Zhang & Qi, 2005).”